Technical Library | Support

Go to the table of contents Go to the previous page Go to the next page View or print as PDF
Introduction to Machine Learning for TRITON AP-DATA : Tuning the classifiers
Tuning the classifiers
Machine Learning | TRITON AP-DATA | v8.3.x | 15-Dec-2016
In some cases, you may wish to tune the classifiers. For example, if too many false positives occur, start by setting the sensitivity level to "Narrow." You can also combine the classifier with other classifiers, such as looking at certain file-types like both Microsoft Office files with PDF files.
If the overall accuracy level is too low, check to see if all your positive examples are related to the same subject. If you have a small number of subjects and enough samples for each of them, you can create a different classifier for each subject by assigning a folder to each subject, locating documents that are related to the subject in the corresponding folder, and then training the system separately on each folder.
In many cases, several small specific classifiers can provide better accuracy than one general classifier.

Go to the table of contents Go to the previous page Go to the next page View or print as PDF
Introduction to Machine Learning for TRITON AP-DATA : Tuning the classifiers
Copyright 2016 Forcepoint LLC. All rights reserved.